mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-27 10:49:52 +00:00
34f9308e1a
* Conversion to df does not need initialization * Apply Black * fix test case * Apply Black Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
72 lines
2.3 KiB
Python
72 lines
2.3 KiB
Python
import pytest
|
|
import pandas as pd
|
|
from pathlib import Path
|
|
|
|
from haystack.utils.preprocessing import convert_files_to_dicts, tika_convert_files_to_dicts
|
|
from haystack.utils.cleaning import clean_wiki_text
|
|
from haystack.utils.augment_squad import augment_squad
|
|
from haystack.utils.squad_data import SquadData
|
|
|
|
from conftest import SAMPLES_PATH
|
|
|
|
|
|
def test_convert_files_to_dicts():
|
|
documents = convert_files_to_dicts(
|
|
dir_path=(SAMPLES_PATH).absolute(), clean_func=clean_wiki_text, split_paragraphs=True
|
|
)
|
|
assert documents and len(documents) > 0
|
|
|
|
|
|
@pytest.mark.tika
|
|
def test_tika_convert_files_to_dicts():
|
|
documents = tika_convert_files_to_dicts(dir_path=SAMPLES_PATH, clean_func=clean_wiki_text, split_paragraphs=True)
|
|
assert documents and len(documents) > 0
|
|
|
|
|
|
def test_squad_augmentation():
|
|
input_ = SAMPLES_PATH / "squad" / "tiny.json"
|
|
output = SAMPLES_PATH / "squad" / "tiny_augmented.json"
|
|
glove_path = SAMPLES_PATH / "glove" / "tiny.txt" # dummy glove file, will not even be use when augmenting tiny.json
|
|
multiplication_factor = 5
|
|
augment_squad(
|
|
model="distilbert-base-uncased",
|
|
tokenizer="distilbert-base-uncased",
|
|
squad_path=input_,
|
|
output_path=output,
|
|
glove_path=glove_path,
|
|
multiplication_factor=multiplication_factor,
|
|
)
|
|
original_squad = SquadData.from_file(input_)
|
|
augmented_squad = SquadData.from_file(output)
|
|
assert original_squad.count(unit="paragraph") == augmented_squad.count(unit="paragraph") * multiplication_factor
|
|
|
|
|
|
def test_squad_to_df():
|
|
df = pd.DataFrame(
|
|
[["title", "context", "question", "id", "answer", 1, False]],
|
|
columns=["title", "context", "question", "id", "answer_text", "answer_start", "is_impossible"],
|
|
)
|
|
|
|
expected_result = [
|
|
{
|
|
"title": "title",
|
|
"paragraphs": [
|
|
{
|
|
"context": "context",
|
|
"qas": [
|
|
{
|
|
"question": "question",
|
|
"id": "id",
|
|
"answers": [{"text": "answer", "answer_start": 1}],
|
|
"is_impossible": False,
|
|
}
|
|
],
|
|
}
|
|
],
|
|
}
|
|
]
|
|
|
|
result = SquadData.df_to_data(df)
|
|
|
|
assert result == expected_result
|